Steve Han
Papers
1
Total Citations
48
H-Index
1
About
Steve Han is a leading researcher in humanoid robotics, with a primary focus on loco-manipulation—the seamless integration of locomotion and object manipulation. His most impactful work addresses one of the field’s hardest challenges: teaching humanoids complex, whole-body skills through deep imitation learning. In his highly cited 2023 paper, Han introduced TRILL, a data-efficient framework that leverages human teleoperation to collect task demonstrations and train robust policies for high-degree-of-freedom humanoids. This breakthrough significantly reduces the data and engineering burden traditionally required for such tasks, enabling more natural and versatile robot behaviors. With 48 citations in just a short time, his work is already shaping how researchers approach skill acquisition in humanoid platforms. Han’s contributions are particularly notable for bridging the gap between human demonstration and robot learning, making advanced loco-manipulation more accessible. His research holds promise for real-world applications in disaster response, manufacturing, and assistive robotics, where humanoids must navigate and interact with human-centered environments.
Research Focus
Key Achievements
Top Papers
- 1